Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 00064v2 Announce Type: replace Abstract: As technology advances, various algorithms have been proposed for air traffic management, yet their operational adoption in tactical control remains limited.
arXiv:2607. 28680v1 Announce Type: cross Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities.
arXiv:2510. 06945v2 Announce Type: replace Abstract: Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evaluation metrics based on the Fisher information matrix (FIM) are effective for predicting their training and prediction performance.
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
arXiv:2607. 29169v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions.
arXiv:2605. 15100v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning.
arXiv:2604. 10475v2 Announce Type: replace Abstract: Modeling household-level decisions is central to many real-world applications, including trip planning, residential mobility and migration, disaster management, etc.
arXiv:2607. 28639v1 Announce Type: cross Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias.
arXiv:2603. 13683v4 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts.
arXiv:2607. 28629v1 Announce Type: new Abstract: The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural understanding of Agentic AI, particularly in separating inference, orchestration, and execution layers for autonomous AI agents.
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv:2510. 23634v4 Announce Type: replace-cross Abstract: Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on sets is preserved, namely $S\subseteq T \text{ if and only if } F(S)\leq F(T) $.
arXiv:2501. 04426v2 Announce Type: replace-cross Abstract: Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift without additional environment interaction.
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv:2607. 29456v1 Announce Type: cross Abstract: Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine learning methods to be used for nuisance parameter estimation while preserving valid inference.
arXiv:2607. 29283v1 Announce Type: cross Abstract: Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most public corpora are now synthesized.
arXiv:2602. 02685v3 Announce Type: replace Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions.
arXiv:2607. 28946v1 Announce Type: new Abstract: Despite its many benefits, widespread access to individuals' personal data also causes severe privacy concerns for consumers, companies, and policymakers.